# lucidrains/stylegan2-pytorch

Simplest working implementation of Stylegan2, state of the art generative adversarial network, in Pytorch. Enabling everyone to experience disentanglement

Repository: https://github.com/lucidrains/stylegan2-pytorch
Canonical: https://ross.abutalabs.com/products/stylegan2-pytorch
Homepage: https://thispersondoesnotexist.com
Language: Python
License: MIT
License Family: permissive
Topics: generative-adversarial-network, artificial-intelligence, pytorch, machine-learning, generative-model
Last push: 2025-01-12T14:04:19+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 1, release rhythm 8, longevity 100
- inputs: {"age_days": 2428, "days_push": 598, "days_rel": 598, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3783, forks 582 (observed 2026-08-28T04:08:18.525891+00:00)

## What it is
A simple PyTorch implementation of StyleGAN2, a state-of-the-art generative adversarial network, trainable entirely from the command line without coding. It lets users train GANs on their own image datasets and generate novel images or latent-space interpolation videos.

## Use cases
- train a GAN on my own image dataset
- generate realistic fake images of faces or objects
- create latent space interpolation videos
- learn how StyleGAN2 works in PyTorch
- generate images of things that don't exist
- experiment with generative adversarial networks without coding

## When to choose
- you want a minimal, easy-to-use StyleGAN2 implementation trainable via CLI
- you have a GPU with CUDA and a folder of training images
- you want a pip-installable package with checkpointing and resumption built in

## When to avoid
- you need the latest GAN architectures or state-of-the-art image quality
- you require distributed or multi-GPU training at scale
- you have no GPU available, since training requires CUDA

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, image-processing, cli
- domain: deep-learning, machine-learning, artificial-intelligence, image-processing
- platform: python, cli, cross-platform
- tags: stylegan2, generative-adversarial-network, pytorch, image-generation, gan, gpu

## Member repositories
- lucidrains/stylegan2-pytorch (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:18.525891+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:27:43.147069+00:00, confidence not recorded.
  - readme: https://github.com/lucidrains/stylegan2-pytorch (fetched 2026-08-28T04:08:18.525891+00:00, sha 7212340cfefe)
  - homepage: https://thispersondoesnotexist.com (fetched 2026-08-29T09:22:19.936839+00:00, sha c7f9e752e087)
  - registry_pypi: https://pypi.org/pypi/stylegan2-pytorch/json (fetched 2026-08-29T09:22:19.946274+00:00, sha a74b9c7bb19d)
- Data as of 2026-08-30T08:39:29.467469+00:00.